Hugging Face's logo

Kobi-01
/
updated_qa_model

Question Answering
Transformers
Safetensors
distilbert
Model card Files
xet
Community
Kobi-01 commited on
Commit
e6d9e12
路
verified 路
1 Parent(s): 5b4d10f

Upload tokenizer

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. sentencepiece.bpe.model +3 -0
  3. special_tokens_map.json +23 -2
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +33 -14
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json CHANGED
@@ -2,7 +2,14 @@
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
5
- "normalized": true,
 
 
 
 
 
 
 
6
  "rstrip": false,
7
  "single_word": false
8
  },
@@ -13,7 +20,21 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
 
 
 
 
 
 
16
  "pad_token": {
 
 
 
 
 
 
 
17
  "content": "</s>",
18
  "lstrip": false,
19
  "normalized": false,
@@ -23,7 +44,7 @@
23
  "unk_token": {
24
  "content": "<unk>",
25
  "lstrip": false,
26
- "normalized": true,
27
  "rstrip": false,
28
  "single_word": false
29
  }
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
  "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
  "content": "</s>",
39
  "lstrip": false,
40
  "normalized": false,
 
44
  "unk_token": {
45
  "content": "<unk>",
46
  "lstrip": false,
47
+ "normalized": false,
48
  "rstrip": false,
49
  "single_word": false
50
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,20 +1,17 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "add_prefix_space": null,
5
  "added_tokens_decoder": {
6
  "0": {
7
- "content": "<unk>",
8
  "lstrip": false,
9
- "normalized": true,
10
  "rstrip": false,
11
  "single_word": false,
12
  "special": true
13
  },
14
  "1": {
15
- "content": "<s>",
16
  "lstrip": false,
17
- "normalized": true,
18
  "rstrip": false,
19
  "single_word": false,
20
  "special": true
@@ -26,18 +23,40 @@
26
  "rstrip": false,
27
  "single_word": false,
28
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  }
30
  },
31
  "bos_token": "<s>",
32
  "clean_up_tokenization_spaces": false,
 
 
33
  "eos_token": "</s>",
34
  "extra_special_tokens": {},
35
- "legacy": true,
36
- "model_max_length": 1000000000000000019884624838656,
37
- "pad_token": "</s>",
 
 
 
38
  "sp_model_kwargs": {},
39
- "tokenizer_class": "LlamaTokenizer",
40
- "unk_token": "<unk>",
41
- "use_default_system_prompt": false,
42
- "use_fast": true
 
43
  }
 
1
  {
 
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "<s>",
5
  "lstrip": false,
6
+ "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "<pad>",
13
  "lstrip": false,
14
+ "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
 
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
  }
43
  },
44
  "bos_token": "<s>",
45
  "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "do_lower_case": false,
48
  "eos_token": "</s>",
49
  "extra_special_tokens": {},
50
+ "full_tokenizer_file": null,
51
+ "mask_token": "<mask>",
52
+ "max_length": 128,
53
+ "model_max_length": 512,
54
+ "pad_token": "<pad>",
55
+ "sep_token": "</s>",
56
  "sp_model_kwargs": {},
57
+ "stride": 0,
58
+ "tokenizer_class": "XLMRobertaTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "<unk>"
62
  }